Cinemo: Consistent and Controllable Image Animation with Motion Diffusion Models

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Tools for merging pretrained large language models.

[EMNLP 2022/2023] Fast Vocabulary Transfer & Multi-word Tokenization

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

For releasing code related to compression methods for transformers, accompanying our publications

C# bindings for llama.cpp for Unity

LEIA: Facilitating Cross-Lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation

Suno AI's Bark model in C/C++ for fast text-to-speech

Fast inference engine for Transformer models

This is the official PyTorch implementation of our paper: "Artistic Style Transfer with Internal-external Learning and Contrastive Learning".

RealPersonaChat: A Realistic Persona Chat Corpus with Interlocutors' Own Personalities

Open weights LLM from Google DeepMind.

A dart binding for llama.cpp library, bringing AI to dart world.

A flutter plugin for OnnxRuntime provides an easy, flexible, and fast Dart API to integrate Onnx models in flutter apps across mobile and desktop platforms.

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

llama.cpp for Flutter

Projeto de aplicativo Web a fim de exibição e controle de animações 3D

ONNX runtime for Flutter.

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

A Flutter widget to draw scribbles and text on a background image or color 🎨

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io

The robust text processing pipeline framework enabling customizable, efficient, and metric-logged text preprocessing.

All-in-one text de-duplication

Utility for behavioral and representational analyses of Language Models